Department of Mechanical and Industrial Engineering, University of Johannesburg, Johannesburg P.O. Box 2028, South Africa.
Sensors (Basel). 2021 Jun 28;21(13):4417. doi: 10.3390/s21134417.
This paper describes the development of a modular unmanned aerial vehicle for the detection and eradication of weeds on farmland. Precision agriculture entails solving the problem of poor agricultural yield due to competition for nutrients by weeds and provides a faster approach to eliminating the problematic weeds using emerging technologies. This research has addressed the aforementioned problem. A quadcopter was built, and components were assembled with light-weight materials. The system consists of the electric motor, electronic speed controller, propellers, frame, lithium polymer (li-po) battery, flight controller, a global positioning system (GPS), and receiver. A sprayer module which consists of a relay, Raspberry Pi 3, spray pump, 12 V DC source, water hose, and the tank was built. It operated in such a way that when a weed is detected based on the deep learning algorithms deployed on the Raspberry Pi, general purpose input/output (GPIO) 17 or GPIO 18 (of the Raspberry Pi) were activated to supply 3.3 V, which turned on a DC relay to spray herbicides accordingly. The sprayer module was mounted on the quadcopter and from the test-running operation conducted, broadleaf and grass weeds were accurately detected and the spraying of herbicides according to the weed type occurred in less than a second.
本文描述了一种用于农田杂草检测和清除的模块化无人机的开发。精准农业需要解决由于杂草争夺养分而导致的农业产量低下的问题,并为使用新兴技术快速消除有问题的杂草提供了一种方法。本研究解决了上述问题。我们构建了一架四旋翼飞行器,并使用轻质材料组装了各个部件。该系统由电动机、电子速度控制器、螺旋桨、框架、锂聚合物(Li-po)电池、飞行控制器、全球定位系统(GPS)和接收器组成。我们还构建了一个喷雾器模块,该模块由继电器、Raspberry Pi 3、喷雾泵、12 V DC 电源、水管和水箱组成。其工作原理是,当基于 Raspberry Pi 上部署的深度学习算法检测到杂草时,通用输入/输出(GPIO)17 或 GPIO 18(Raspberry Pi 的 GPIO)被激活,以提供 3.3 V 的电压,从而打开直流继电器,相应地喷洒除草剂。喷雾器模块安装在四旋翼飞行器上,通过进行的测试运行,该系统能够准确检测阔叶杂草和禾本科杂草,并能在不到一秒的时间内根据杂草类型喷洒除草剂。